Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare the generic mutation/open-world profile, while the description adds the operationally critical facts: sessions consume the account's LIVEAIHELP minute balance, an offline expert means a FIFO queue requiring polling of check_queue, and chat is preferred for agents. These are exactly the side effects and workflow constraints an agent needs before invoking, and nothing contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences, each carrying distinct information: purpose, session mechanics, billing, queue fallback, and mode recommendation. The core action is front-loaded and no sentence repeats the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no output schema and clear enumeration of the queue workflow, the definition covers what an agent needs to invoke correctly. It stops short of describing what a successful hire returns (session ID, connection details) or how the session is closed, but end_session and read_messages siblings imply that lifecycle.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are already documented, so a baseline of 3 applies. The description adds marginal value by explaining why mode matters ("Chat mode is recommended for AI agents"), which effectively steers the enum choice beyond the schema's terse "Defaults to chat."

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ("Hire a live vetted human expert") and clarifies the interaction model: a real-time chat or video session where the expert works the problem with you. This is clearly distinguishable from siblings like check_balance, read_messages, or end_session, which are supporting tools inside the session.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the condition for use (help with a task) and explicitly hands off to a named sibling when no expert is online: "you are placed in a FIFO holding queue — poll check_queue until matched." It also recommends chat mode for AI agents. It lacks an explicit negative case (e.g., when not to hire an expert), so it falls just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.